Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Performance of Gait Classifications Using Machine Learning

TL;DR

This study systematically compares various data preprocessing methods to determine their impact on machine learning-based gait classification performance, aiming to establish standardized procedures for improved robustness and comparability.

Contribution

It provides the first systematic comparison of preprocessing combinations and their effects on gait classification accuracy using multiple machine learning models.

Findings

Certain preprocessing combinations significantly improve classification accuracy.

Standardized preprocessing protocols can enhance model robustness.

Recommendations for preprocessing steps tailored to gait analysis are proposed.

Abstract

Human movements are characterized by highly non-linear and multi-dimensional interactions within the motor system. Recently, an increasing emphasis on machine-learning applications has led to a significant contribution to the field of gait analysis, e.g., in increasing the classification performance. In order to ensure the generalizability of the machine-learning models, different data preprocessing steps are usually carried out to process the measured raw data before the classifications. In the past, various methods have been used for each of these preprocessing steps. However, there are hardly any standard procedures or rather systematic comparisons of these different methods and their impact on the classification performance. Therefore, the aim of this analysis is to compare different combinations of commonly applied data preprocessing steps and test their effects on the classification performance of gait patterns. A publicly available dataset on intra-individual changes of gait patterns was used for this analysis. Forty-two healthy participants performed 6 sessions of 15 gait trials for 1 day. For each trial, two force plates recorded the 3D ground reaction forces (GRFs). The data was preprocessed with the following steps: GRF filtering, time derivative, time normalization, data reduction, weight normalization and data scaling. Subsequently, combinations of all methods from each preprocessing step were analyzed by comparing their prediction performance in a six-session classification using Support Vector Machines, Random Forest Classifiers, Multi-Layer Perceptrons, and Convolutional Neural Networks. In conclusion, the present results provide first domain-specific recommendations for commonly applied data preprocessing methods and might help to build more comparable and more robust classification models based on machine learning that are suitable for a practical application.